"LightRAG: Simple and Fast Retrieval-Augmented Generation"

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capabilities.

Preswald is a WASM packager for Python-based interactive data apps: bundle full complex data workflows, particularly visualizations, into single files, runnable completely in-browser, using Pyodide, DuckDB, Pandas, and Plotly, Matplotlib, etc. Build dashboards, reports, and notebooks that run offline, load fast, and share like a document.

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

(Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models.

Zotero chat PDF with AI, DeepSeek, GPT 4.1, ChatGPT, Claude, Gemini, Qwen3

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

A highly optimized LLM inference acceleration engine for Llama and its variants.

LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.

Dynamiq is an orchestration framework for agentic AI and LLM applications

AI assisted programming in Emacs with Aider

A simple example implementation of the VoiceRAG pattern to power interactive voice generative AI experiences using RAG with Azure AI Search and Azure OpenAI's gpt-4o-realtime-preview model.

A lightning-fast, cross-platform AI chat application built with React Native.

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体！

Codai is an AI code assistant that helps developers through a session-based CLI, providing intelligent code suggestions, refactoring, and code reviews based on the full context of the project.

🐸 Read Frog - Open Source Immersive Translate | 🐸 陪读蛙 - 开源沉浸式翻译

A Survey of Spoken Dialogue Models (60 pages)

Dingo: A Comprehensive AI Data Quality Evaluation Tool

Kolosal AI is an OpenSource and Lightweight alternative to LM Studio to run LLMs 100% offline on your device.

Engy is an AI-powered development tool that generates fully functional web applications from natural language, streamlining the process from idea to working prototype.

An extensible framework for building and hosting AI character interactions. Built with pure JS, Fount offers unparalleled flexibility via modular components, custom AI source integration, powerful plugins, and a seamless cross-platform chat experience.

鱼皮的 AI 知识库，汇总热门的 AI 大模型和工具，比如 Deepseek 使用指南、提示词技巧分享、知识干货、应用场景、AI 变现、行业资讯、教程资源等一系列内容，帮助你快速掌握 AI 技术，走在时代前沿。涉及的大模型：chatGPT、Deepseek、Deepseek-r1、QWEN、GROK 等等

Emacs AI Pair Programming Solution

Add AI capabilities to your file system using Ollama, Groq, OpenAi and other's api

Ollama负载均衡服务器 | 一款高性能、易配置的开源负载均衡服务器，优化Ollama负载。它能够帮助您提高应用程序的可用性和响应速度，同时确保系统资源的有效利用。

Benchmark that evaluates LLMs using 651 NYT Connections puzzles extended with extra trick words

✨✨Latest Advances on Neuro-Symbolic Learning in the era of Large Language Models

An AI Powered README Generator for Python Projects to Automate Your Documentation. AI驱动的项目文档生成神器

The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".

[CoRL 2024] VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding

It's an automatic sign-up for a Windsurf account, so you only need an email address to get unlimited access to windsurf's premium features..这是一个自动注册 Windsurf 账号的工具，你只需要一个邮箱即可无限使用windsurf高级功能。

Interleaving Reasoning: Next-Generation Reasoning Systems for AGI

Build AI powered websites with Astro, Shadcn and Vercel AI SDK

最新ChatGPT Plus合租攻略：国内最靠谱的ChatGPT Plus拼车平台推荐(每月仅27元)！可使用GPT-4o生图功能和GPT-4.1系列模型，还支持满血版DeepSeek-R1、马斯克的Grok-3和谷歌Gemini-2.5 Pro！如果你无法解决科学上网的问题，或觉得每月20美元的会员费用过高，可以考虑ChatGPT Plus共享合租帐号。这种方式不仅能够降低使用成本，还免去了科学上网的复杂操作。

[NeurIPS 2024] Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective

This is the repo of developing reasoning models in the specific domain of financial, aim to enhance models capabilities in handling financial reasoning tasks.

comfyui-deepseek-r1 节点插件.Comfyui-deepseek-r1 Node Plugin;智王发布deepseek-r1懒人包，解压即用;Deepseek-r1 Lazy Package, easy to decompress and use

[ICLR 2025] Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation

✨ 让经典名言焕发新生！基于LLM模型动态生成创意故事，用AI重新诠释金山每日一句的智慧结晶

Official Implementation for EMNLP 2024 (main) "AgentReview: Exploring Academic Peer Review with LLM Agent."

Graph Foundation Model for Retrieval Augmented Generation

Free tool to create viral videos from YouTube, generating clips optimized for TikTok and Instagram with automatic transcription and 9:16 editing.

The GenAI API wrapper for Delphi is designed to seamlessly integrate OpenAI's latest models (GPT-4o, o3, o4, and GPT-4.1), providing robust functionality for chat or response interactions for agents, text generation, vision processing, audio analysis, JSON configuration, web search, and asynchronous operations. Image generation with gpt-image-1

A CLI tool to provide LLM context for coding projects by combining project files into a single text file (or clipboard text) with directory tree structure.

AI-powered computer control for automated testing. Factifai uses vision models (Claude, GPT-4o, Gemini) to interact with applications naturally - clicking, typing, and verifying results just like a human would.

Experimental playground for benchmarking language model (LM) architectures, layers, and tricks on smaller datasets. Designed for flexible experimentation and exploration.

The prompts which could enable GPT-4o to think and act like GPT-o1-mini

AI tools collection for students and researchers. 学生和研究人员的AI工具合集。

Meet WebHive, the AI-powered browser that takes care of tasks for you. No more endless clicks, tell it what you need, and it gets it done.

Interact with OpenAI and OpenAI-compatible chat completion APIs in a simple and elegant way. Supports Cohere V2, Groq, Ollama, OpenRouter, Together AI, Perplexity, and more.

An LLM library for Ruby

A TypeScript library for building orchestrated framework-agnostic multi-agent AI systems

fnord is an AI-powered conversational interface to your code, docs, and notes.

Splicing: Gen-AI Copilot for Data Engineering

An completely Free & Unlimited unofficial Python SDK for the OpenAI API, providing seamless integration and easy-to-use methods for interacting with OpenAI's latest powerful AI models, including GPT-4o (Including gpt-4o-audio-preview & gpt-4o-realtime-preview Models), GPT-4, GPT-3.5 Turbo, DALL·E 3, Whisper & Text-to-Speech (TTS) models

一个开源的，专注于提示词管理的平台

DuckDuckGo AI to OpenAI API

Roblox Electron Executor is one of the most favorite Roblox Executors at the moment. Before I tell you how to download Electron Executor, let me tell you that it is currently available safely for Windows. But it is not officially available for Android users as of now but the update is coming and will be launched soon.

Roblox Electron Executor is one of the most favorite Roblox Executors at the moment. Before I tell you how to download Electron Executor, let me tell you that it is currently available safely for Windows. But it is not officially available for Android users as of now but the update is coming and will be launched soon.

Code for the paper: Sketch2Code: Evaluating Vision-Language Models for Interactive Web Design Prototyping

A calculator to estimate the number of tokens and cost associated with processing images using Azure OpenAI's multimodal models

Collection of the most effective AI agents and tools. 'awesome-best-ai-agent' gathers top open-source AI agent projects, including automation tools, GPT-based agents, and more. Ideal for developers and researchers exploring cutting-edge AI capabilities and automation workflows.

🤖 nGPT - A lightning-fast CLI tool that brings any OpenAI-compatible LLM (OpenAI, Ollama, Groq, Claude, Gemini) directly to your terminal. Generate code, craft git commits, execute shell commands, rewrite text, and chat interactively, all with seamless provider switching and real-time streaming.

[NeurIPS'24] SpatialEval: a benchmark to evaluate spatial reasoning abilities of MLLMs and LLMs

VUDA is an autonomous debugging agent that empowers AI models to visually analyze, test, and debug web

A FastAPI application that relays client WebSocket connections to OpenAI's Realtime API, enabling seamless integration for real-time speech-to-speech interactions

Streamlit Multi AI Platform Chat App

Highest priest GPT

File maid powered by large language models (Ollama/OpenAI)

CLI tool that helps you write clear, concise, and AI-generated commit messages using OpenRouter's LLM models.

点点现聊，是一款功能丰富、现代化的 Web 聊天应用，它利用 WebRTC 进行用户间的直接媒体通信，支持文本、文件共享、语音消息以及实时音频/视频/屏幕共享通话。通过基于 WebSocket 的信令服务器（由Java Spring Boot实现）完成初始用户发现和连接协商。WebRTC 通讯减少了对中央服务器传输大量媒体数据的依赖（除信令与可选的 TURN 中继服务外），而AI聊天和TTS功能则通过后端代理与外部服务交互。该应用深度集成了具有文本转语音（TTS）功能的主题化AI助手联系人，AI角色拥有动态上下文（如每日随机事件和心情）并支持长对话智能摘要，带来更生动的交互体验。

한국어 논문 요약 및 Q&A 디스코드 챗봇

【国内直连】ChatGPT国内中文版镜像网站整理（2024/12/10）

ai-auto-crawler: puppeteer + autogen

🐱🐾基于大模型的 ACM-ICPC 算法题目自动出题系统，可以自动生成算法题目、测试用例和题解代码。系统可以作为一个单独的服务运行，也可以作为一个模块集成到 OJ 系统中。

A lightweight GPT-style large language model (LLM) with high parameter and memory efficiency.

A Discord Bot using LLMs

DeepGPT4.5是一个创新的人工智能应用，将DeepSeek R1模型的思维链能力与GPT-4.5的强大推理能力相结合。通过这种结合，我们能够获得更深入、更全面的AI推理结果，同时为用户提供思维过程的透明度。

Chat with an LLM

Qwen-TTS offers a robust voice synthesis service using FastAPI, supporting bilingual and dialect options. Explore seamless audio generation on GitHub! 🚀🌟

AzChat - Chat with Azure OpenAI Service

Multimodal-VideoRAG: Using BridgeTower Embeddings and Large Vision Language Models

Python package that provides a connector for integrating the Cel.ai framework with Chatwoot.

Electron-Executor is a powerful tool for executing commands directly from an Electron application. It provides a seamless way to interact with the underlying operating system for enhanced functionality.

Open-Research.ai is an AI-driven search engine that leverages OpenAI and Serper.dev to deliver a powerful search experience. 1-Click deploy to Vercel.

Commify: You Should Commit Yourself. Commify is a CLI tool that generates meaningful, structured commit messages for Git repositories using AI.

🤖 A lightweight desktop tool for developers working with AI assistants. 📊 Visualize project structure, 📋 selectively export file paths and code to clipboard, making collaboration with ChatGPT, Claude and other AI assistants more efficient. 🌐 Supports multi-language UI, 🔍 file filtering, and ⚙️ customizable output formats.

GPT4o, GPT4o-mini, and GPT4 Turbo jailbreak prompt for Research/IoC Development Purposes

Open source platform for building AI agents

A CLI program based on python, and using GPT to help you deal with i18n

Free GPT-4o mini telegram chat with voice and text recognition in photos

Ask AI unofficial client

国内ChatGPT中文版镜像网站整理【2024/11/24】。汇总整理国内ChatGPT-4中文版镜像网站，帮助国内在正常网络下也能访问ChatGPT

o1 and GPT-4o system prompts

2024年11月最新 国内ChatGPT中文版镜像网站整理。汇总整理国内ChatGPT-4中文版镜像网站整理

This project is built with **Ollama** and **TinyLlama** to create a lightweight Large Language Model (LLM) application. The backend, powered by Express.js, processes requests and communicates with the TinyLlama model, while the frontend, developed in React.js, provides a user-friendly interface for interaction.

Minimal Express.js server with simple web client that works with Azure OpenAI & OpenAI endpoints.Supports /v1/responses and /v1/chat/completions,audio and DeepSeek models. Highlights:1.Streaming text & audio with "Stop" button 2.Key and keyless Entra ID authentication for in Azure OpenAI 3.Code- and Text- puzzles 5.Difference in models' performance